Bayesian classification and unsupervised learning for isolating weeds in row crops

Pattern Analysis and Applications - Tập 17 - Trang 401-414 - 2012
François-Michel De Rainville1, Audrey Durand1, Félix-Antoine Fortin1, Kevin Tanguy1, Xavier Maldague1, Bernard Panneton2, Marie-Josée Simard3
1Laboratoire de vision et systèmes numériques, Département de génie électrique et de génie informatique, Université Laval, Quebec, Canada
2Centre de recherche et de développement en horticulture, Agriculture et Agroalimentaire Canada, St-Jean-sur-Richelieu, Canada
3Centre de recherche et de développement sur les sols et les grandes cultures, Agriculture et Agroalimentaire Canada, Quebec, Canada

Tóm tắt

This paper presents a weed/crop classification method using computer vision and morphological analysis. Subsequent supervised and unsupervised learning methods are applied to extract dominant morphological characteristics of weeds present in corn and soybean fields. The novelty of the presented technique resides in the feature extraction process that is based on spatial localization of vegetation in fields. Features from the weed leaf area distribution are extracted from the cultivation inter-rows, then features from the crop are inferred from the mixture model equation. Those extracted features are then passed to a naive bayesian classifier and a gaussian mixture clustering algorithm to discriminate weed from crop plant. The presented technique correctly classifies an average of 94 % of corn and soybean plants and 85 % of the weed (multiple species) without any prior knowledge on the species present in the field.

Tài liệu tham khảo

Aitkenhead M.J., Dalgetty I.A., Mullins C.E., McDonald A.J.S., Strachan N.J.C. (2003) Weed and crop discrimination using image analysis and artificial intelligence methods. Computers and Electronics in Agriculture 39(3):157–171 Alpaydin E (2010) Introduction to machine learning, 2nd edn. MIT Press, USA Asif M, Amir S, Israr A, Faraz M (2010) A vision system for autonomous weed detection robot. Int J Comput Electr Eng 2(3):486–491 Bowman A, Azzalini A (1997) Applied smoothing techniques for data analysis. Clarendon Press, Oxford DeLorenzo M.E., Scott G.I., Ross P.E. (2001) Toxicity of pesticides to aquatic microorganisms: a review. Environmental Toxicology and Chemistry 20(1):84–98 Dempster A.P., Laird N.M., Rubin D.B. (1977) Maximum likelihood estimation from incomplete data via the EM algorithm. Journal of the Royal Statistical Society Series B (Methodological) 39:1–38 Figueiredo M.A.T., Jain A.K. (2002) Unsupervised learning of finite mixture models. IEEE Transaction on Pattern Analysis and Machine Intelligence 24(3):381–396 Freemark K., Boutin C. (1995) Impacts of agricultural herbicide use on terrestrial wildlife in temperate landscapes: A review with special reference to north america. Agriculture, Ecosystems & Environment 52(2):67–91 Hemming J., Rath T. (2001) Precision Agriculture Computer-Vision-based Weed Identification under Field Conditions using Controlled Lighting. Journal of Agricultural Engineering Research 78(3):233–243 Hough P.V.C. (1962) A Method and Means for Recognizing Complex Patterns. U.S. Patent 3,069,654 Jones G., Gée C., Truchetet F. (2009) Assessment of an inter-row weed infestation rate on simulated agronomic images. Computers and Electronics in Agriculture 67(1-2):43–50 Longchamps L., Panneton B., Samson G., Leroux G., Thériault R. (2010) Discrimination of corn, grasses and dicot weeds by their uv-induced fluorescence spectral signature. Precision Agric 11:181–197 Ngouajio M., Lemieux C., Fortier J.J., Careau D., Leroux G.D. (1998) Validation of an operator-assisted module to measure weed and crop leaf cover by digital image analysis. Weed Technol 12(3):446–453 Otsu N. (1979) A threshold selection method from gray-level histograms. IEEE Transaction on Systems, Man, and Cybernetics 9(1):62–66 Panneton B (2009) Initiative des stratégies de réduction des risques liés aux pesticides. Rapport annuel PRR07–10, Centre pour la lutte antiparasitaire-Agriculture et Agroalimentaire Canada Panneton B., Brouillard M. (2009) Colour representation methods for segmentation of vegetation in photographs. Biosyst Eng 102:365–378 Panneton B. Simard MJ, Leroux GD, Légére A (2010) Mise au point et impact sur la distribution spatio-temporelle des adventices d’un système d’aide ála décision pour l’application des herbicides en maïs-soya. Rapport final PRR07–10, Centre pour la lutte antiparasitaire-Agriculture et Agroalimentaire Canada Parzen E. (1962) On estimation of a probability density function and mode. Annals of Mathematical Statistics 33:1065–1076 Rosenblatt M. (1956) Remarks on some nonparametric estimates of a density function. Annals of Mathematical Statistics 27:832–837 Slaughter D.C., Giles D.K., Downey D. (2008) Autonomous robotic weed control systems: A review.Computers and Electronics in Agriculture 61(1):63–78 doi:10.1016/j.compag.2007.05.008 Stafford J.V. (2000) Implementing precision agriculture in the 21th century. J Agric Eng Res 76:267–275 Tellaeche A., Pajares G., Burgos-Artizzu X.P., Ribeiro A. (2011) A computer vision approach for weeds identification through Support Vector Machines. Applied Soft Computing 11(1):908–915 Timmermann C., Gerhards R., Kuhbauch W. (2003) The economic impact of site-specific weed control. Precision Agric 4(3):249–260 Yang C.C., Prasher S.O., Landry J.A., Ramaswamy H.S. (2003) Development of an image processing system and a fuzzy algorithm for site-specific herbicide applications. Precision Agric 4(1):5–18 Åstrand B., Baerveldt A.J. (2005) A vision based row-following system for agricultural field machinery. Mechatronics 15(2):251–269